July 29, 2019

3156 words 15 mins read

Paper Group ANR 42

Likelihood Estimation for Generative Adversarial Networks. Spectral-spatial classification of hyperspectral images: three tricks and a new supervised learning setting. Does Normalization Methods Play a Role for Hyperspectral Image Classification?. Asynchronous Announcements. Continuous Multimodal Emotion Recognition Approach for AVEC 2017. Signal a …

Likelihood Estimation for Generative Adversarial Networks


Title	Likelihood Estimation for Generative Adversarial Networks
Authors	Hamid Eghbal-zadeh, Gerhard Widmer
Abstract	We present a simple method for assessing the quality of generated images in Generative Adversarial Networks (GANs). The method can be applied in any kind of GAN without interfering with the learning procedure or affecting the learning objective. The central idea is to define a likelihood function that correlates with the quality of the generated images. In particular, we derive a Gaussian likelihood function from the distribution of the embeddings (hidden activations) of the real images in the discriminator, and based on this, define two simple measures of how likely it is that the embeddings of generated images are from the distribution of the embeddings of the real images. This yields a simple measure of fitness for generated images, for all varieties of GANs. Empirical results on CIFAR-10 demonstrate a strong correlation between the proposed measures and the perceived quality of the generated images.
Tasks
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07530v1
PDF	http://arxiv.org/pdf/1707.07530v1.pdf
PWC	https://paperswithcode.com/paper/likelihood-estimation-for-generative
Repo
Framework

Spectral-spatial classification of hyperspectral images: three tricks and a new supervised learning setting


Title	Spectral-spatial classification of hyperspectral images: three tricks and a new supervised learning setting
Authors	Jacopo Acquarelli, Elena Marchiori, Lutgarde M. C. Buydens, Thanh Tran, Twan van Laarhoven
Abstract	Spectral-spatial classification of hyperspectral images has been the subject of many studies in recent years. In the presence of only very few labeled pixels, this task becomes challenging. In this paper we address the following two research questions: 1) Can a simple neural network with just a single hidden layer achieve state of the art performance in the presence of few labeled pixels? 2) How is the performance of hyperspectral image classification methods affected when using disjoint train and test sets? We give a positive answer to the first question by using three tricks within a very basic shallow Convolutional Neural Network (CNN) architecture: a tailored loss function, and smooth- and label-based data augmentation. The tailored loss function enforces that neighborhood wavelengths have similar contributions to the features generated during training. A new label-based technique here proposed favors selection of pixels in smaller classes, which is beneficial in the presence of very few labeled pixels and skewed class distributions. To address the second question, we introduce a new sampling procedure to generate disjoint train and test set. Then the train set is used to obtain the CNN model, which is then applied to pixels in the test set to estimate their labels. We assess the efficacy of the simple neural network method on five publicly available hyperspectral images. On these images our method significantly outperforms considered baselines. Notably, with just 1% of labeled pixels per class, on these datasets our method achieves an accuracy that goes from 86.42% (challenging dataset) to 99.52% (easy dataset). Furthermore we show that the simple neural network method improves over other baselines in the new challenging supervised setting. Our analysis substantiates the highly beneficial effect of using the entire image (so train and test data) for constructing a model.
Tasks	Classification Of Hyperspectral Images, Data Augmentation, Hyperspectral Image Classification, Image Classification
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05512v4
PDF	http://arxiv.org/pdf/1711.05512v4.pdf
PWC	https://paperswithcode.com/paper/spectral-spatial-classification-of-1
Repo
Framework

Does Normalization Methods Play a Role for Hyperspectral Image Classification?


Title	Does Normalization Methods Play a Role for Hyperspectral Image Classification?
Authors	Faxian Cao, Zhijing Yang, Jinchang Ren, Mengying Jiang, Wing-Kuen Ling
Abstract	For Hyperspectral image (HSI) datasets, each class have their salient feature and classifiers classify HSI datasets according to the class’s saliency features, however, there will be different salient features when use different normalization method. In this letter, we report the effect on classifiers by different normalization methods and recommend the best normalization methods for classifier after analyzing the impact of different normalization methods on classifiers. Pavia University datasets, Indian Pines datasets and Kennedy Space Center datasets will apply to several typical classifiers in order to evaluate and analysis the impact of different normalization methods on typical classifiers.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2017-10-09
URL	http://arxiv.org/abs/1710.02939v1
PDF	http://arxiv.org/pdf/1710.02939v1.pdf
PWC	https://paperswithcode.com/paper/does-normalization-methods-play-a-role-for
Repo
Framework

Asynchronous Announcements


Title	Asynchronous Announcements
Authors	Philippe Balbiani, Hans van Ditmarsch, Saúl Fernandez Gonzalez
Abstract	We propose a multi-agent epistemic logic of asynchronous announcements, where truthful announcements are publicly sent but individually received by agents, and in the order in which they were sent. Additional to epistemic modalities the logic contains dynamic modalities for making announcements and for receiving them. What an agent believes is a function of her initial uncertainty and of the announcements she has received. Beliefs need not be truthful, because announcements already made may not yet have been received. As announcements are true when sent, certain message sequences can be ruled out, just like inconsistent cuts in distributed computing. We provide a complete axiomatization for this \emph{asynchronous announcement logic} (AA). It is a reduction system that also demonstrates that any formula in $AA$ is equivalent to one without dynamic modalities, just as for public announcement logic. The model checking complexity is in PSPACE. A detailed example modelling message exchanging processes in distributed computing in $AA$ closes our investigation.
Tasks
Published	2017-05-08
URL	https://arxiv.org/abs/1705.03392v3
PDF	https://arxiv.org/pdf/1705.03392v3.pdf
PWC	https://paperswithcode.com/paper/asynchronous-announcements
Repo
Framework

Continuous Multimodal Emotion Recognition Approach for AVEC 2017


Title	Continuous Multimodal Emotion Recognition Approach for AVEC 2017
Authors	Narotam Singh, Nittin Singh, Abhinav Dhall
Abstract	This paper reports the analysis of audio and visual features in predicting the continuous emotion dimensions under the seventh Audio/Visual Emotion Challenge (AVEC 2017), which was done as part of a B.Tech. 2nd year internship project. For visual features we used the HOG (Histogram of Gradients) features, Fisher encodings of SIFT (Scale-Invariant Feature Transform) features based on Gaussian mixture model (GMM) and some pretrained Convolutional Neural Network layers as features; all these extracted for each video clip. For audio features we used the Bag-of-audio-words (BoAW) representation of the LLDs (low-level descriptors) generated by openXBOW provided by the organisers of the event. Then we trained fully connected neural network regression model on the dataset for all these different modalities. We applied multimodal fusion on the output models to get the Concordance correlation coefficient on Development set as well as Test set.
Tasks	Emotion Recognition, Multimodal Emotion Recognition
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05861v2
PDF	http://arxiv.org/pdf/1709.05861v2.pdf
PWC	https://paperswithcode.com/paper/continuous-multimodal-emotion-recognition
Repo
Framework

Signal and Noise Statistics Oblivious Sparse Reconstruction using OMP/OLS


Title	Signal and Noise Statistics Oblivious Sparse Reconstruction using OMP/OLS
Authors	Sreejith Kallummil, Sheetal Kalyani
Abstract	Orthogonal matching pursuit (OMP) and orthogonal least squares (OLS) are widely used for sparse signal reconstruction in under-determined linear regression problems. The performance of these compressed sensing (CS) algorithms depends crucially on the \textit{a priori} knowledge of either the sparsity of the signal ($k_0$) or noise variance ($\sigma^2$). Both $k_0$ and $\sigma^2$ are unknown in general and extremely difficult to estimate in under determined models. This limits the application of OMP and OLS in many practical situations. In this article, we develop two computationally efficient frameworks namely TF-IGP and RRT-IGP for using OMP and OLS even when $k_0$ and $\sigma^2$ are unavailable. Both TF-IGP and RRT-IGP are analytically shown to accomplish successful sparse recovery under the same set of restricted isometry conditions on the design matrix required for OMP/OLS with \textit{a priori} knowledge of $k_0$ and $\sigma^2$. Numerical simulations also indicate a highly competitive performance of TF-IGP and RRT-IGP in comparison to OMP/OLS with \textit{a priori} knowledge of $k_0$ and $\sigma^2$.
Tasks
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08712v1
PDF	http://arxiv.org/pdf/1707.08712v1.pdf
PWC	https://paperswithcode.com/paper/signal-and-noise-statistics-oblivious-sparse
Repo
Framework

Extreme Sparse Multinomial Logistic Regression: A Fast and Robust Framework for Hyperspectral Image Classification


Title	Extreme Sparse Multinomial Logistic Regression: A Fast and Robust Framework for Hyperspectral Image Classification
Authors	Faxian Cao, Zhijing Yang, Jinchang Ren, Wing-Kuen Ling
Abstract	Although the sparse multinomial logistic regression (SMLR) has provided a useful tool for sparse classification, it suffers from inefficacy in dealing with high dimensional features and manually set initial regressor values. This has significantly constrained its applications for hyperspectral image (HSI) classification. In order to tackle these two drawbacks, an extreme sparse multinomial logistic regression (ESMLR) is proposed for effective classification of HSI. First, the HSI dataset is projected to a new feature space with randomly generated weight and bias. Second, an optimization model is established by the Lagrange multiplier method and the dual principle to automatically determine a good initial regressor for SMLR via minimizing the training error and the regressor value. Furthermore, the extended multi-attribute profiles (EMAPs) are utilized for extracting both the spectral and spatial features. A combinational linear multiple features learning (MFL) method is proposed to further enhance the features extracted by ESMLR and EMAPs. Finally, the logistic regression via the variable splitting and the augmented Lagrangian (LORSAL) is adopted in the proposed framework for reducing the computational time. Experiments are conducted on two well-known HSI datasets, namely the Indian Pines dataset and the Pavia University dataset, which have shown the fast and robust performance of the proposed ESMLR framework.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02517v2
PDF	http://arxiv.org/pdf/1709.02517v2.pdf
PWC	https://paperswithcode.com/paper/extreme-sparse-multinomial-logistic
Repo
Framework

Boosting with Lexicographic Programming: Addressing Class Imbalance without Cost Tuning


Title	Boosting with Lexicographic Programming: Addressing Class Imbalance without Cost Tuning
Authors	Shounak Datta, Sayak Nag, Swagatam Das
Abstract	A large amount of research effort has been dedicated to adapting boosting for imbalanced classification. However, boosting methods are yet to be satisfactorily immune to class imbalance, especially for multi-class problems. This is because most of the existing solutions for handling class imbalance rely on expensive cost set tuning for determining the proper level of compensation. We show that the assignment of weights to the component classifiers of a boosted ensemble can be thought of as a game of Tug of War between the classes in the margin space. We then demonstrate how this insight can be used to attain a good compromise between the rare and abundant classes without having to resort to cost set tuning, which has long been the norm for imbalanced classification. The solution is based on a lexicographic linear programming framework which requires two stages. Initially, class-specific component weight combinations are found so as to minimize a hinge loss individually for each of the classes. Subsequently, the final component weights are assigned so that the maximum deviation from the class-specific minimum loss values (obtained in the previous stage) is minimized. Hence, the proposal is not only restricted to two-class situations, but is also readily applicable to multi-class problems. Additionally,we also derive the dual formulation corresponding to the proposed framework. Experiments conducted on artificial and real-world imbalanced datasets as well as on challenging applications such as hyperspectral image classification and ImageNet classification establish the efficacy of the proposal.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2017-08-31
URL	http://arxiv.org/abs/1708.09684v2
PDF	http://arxiv.org/pdf/1708.09684v2.pdf
PWC	https://paperswithcode.com/paper/boosting-with-lexicographic-programming
Repo
Framework

Unsupervised Object Discovery and Segmentation of RGBD-images


Title	Unsupervised Object Discovery and Segmentation of RGBD-images
Authors	Johan Ekekrantz, Nils Bore, Rares Ambrus, John Folkesson, Patric Jensfelt
Abstract	In this paper we introduce a system for unsupervised object discovery and segmentation of RGBD-images. The system models the sensor noise directly from data, allowing accurate segmentation without sensor specific hand tuning of measurement noise models making use of the recently introduced Statistical Inlier Estimation (SIE) method. Through a fully probabilistic formulation, the system is able to apply probabilistic inference, enabling reliable segmentation in previously challenging scenarios. In addition, we introduce new methods for filtering out false positives, significantly improving the signal to noise ratio. We show that the system significantly outperform state-of-the-art in on a challenging real-world dataset.
Tasks
Published	2017-10-18
URL	http://arxiv.org/abs/1710.06929v1
PDF	http://arxiv.org/pdf/1710.06929v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-object-discovery-and
Repo
Framework

Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification


Title	Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification
Authors	Qingshan Liu, Feng Zhou, Renlong Hang, Xiaotong Yuan
Abstract	This paper proposes a novel deep learning framework named bidirectional-convolutional long short term memory (Bi-CLSTM) network to automatically learn the spectral-spatial feature from hyperspectral images (HSIs). In the network, the issue of spectral feature extraction is considered as a sequence learning problem, and a recurrent connection operator across the spectral domain is used to address it. Meanwhile, inspired from the widely used convolutional neural network (CNN), a convolution operator across the spatial domain is incorporated into the network to extract the spatial feature. Besides, to sufficiently capture the spectral information, a bidirectional recurrent connection is proposed. In the classification phase, the learned features are concatenated into a vector and fed to a softmax classifier via a fully-connected operator. To validate the effectiveness of the proposed Bi-CLSTM framework, we compare it with several state-of-the-art methods, including the CNN framework, on three widely used HSIs. The obtained results show that Bi-CLSTM can improve the classification performance as compared to other methods.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2017-03-23
URL	http://arxiv.org/abs/1703.07910v1
PDF	http://arxiv.org/pdf/1703.07910v1.pdf
PWC	https://paperswithcode.com/paper/bidirectional-convolutional-lstm-based
Repo
Framework

Safe and Nested Subgame Solving for Imperfect-Information Games


Title	Safe and Nested Subgame Solving for Imperfect-Information Games
Authors	Noam Brown, Tuomas Sandholm
Abstract	In imperfect-information games, the optimal strategy in a subgame may depend on the strategy in other, unreached subgames. Thus a subgame cannot be solved in isolation and must instead consider the strategy for the entire game as a whole, unlike perfect-information games. Nevertheless, it is possible to first approximate a solution for the whole game and then improve it by solving individual subgames. This is referred to as subgame solving. We introduce subgame-solving techniques that outperform prior methods both in theory and practice. We also show how to adapt them, and past subgame-solving techniques, to respond to opponent actions that are outside the original action abstraction; this significantly outperforms the prior state-of-the-art approach, action translation. Finally, we show that subgame solving can be repeated as the game progresses down the game tree, leading to far lower exploitability. These techniques were a key component of Libratus, the first AI to defeat top humans in heads-up no-limit Texas hold’em poker.
Tasks
Published	2017-05-08
URL	http://arxiv.org/abs/1705.02955v3
PDF	http://arxiv.org/pdf/1705.02955v3.pdf
PWC	https://paperswithcode.com/paper/safe-and-nested-subgame-solving-for-imperfect
Repo
Framework

Information Theoretic Optimal Learning of Gaussian Graphical Models


Title	Information Theoretic Optimal Learning of Gaussian Graphical Models
Authors	Sidhant Misra, Marc Vuffray, Andrey Y. Lokhov
Abstract	What is the optimal number of independent observations from which a sparse Gaussian Graphical Model can be correctly recovered? Information-theoretic arguments provide a lower bound on the minimum number of samples necessary to perfectly identify the support of any multivariate normal distribution as a function of model parameters. For a model defined on a sparse graph with $p$ nodes, a maximum degree $d$ and minimum normalized edge strength $\kappa$, this necessary number of samples scales at least as $d \log p/\kappa^2$. The sample complexity requirements of existing methods for perfect graph reconstruction exhibit dependency on additional parameters that do not enter in the lower bound. The question of whether the lower bound is tight and achievable by a polynomial time algorithm remains open. In this paper, we constructively answer this question and propose an algorithm, termed DICE, whose sample complexity matches the information-theoretic lower bound up to a universal constant factor. We also propose a related algorithm SLICE that has a slightly higher sample complexity, but can be implemented as a mixed integer quadratic program which makes it attractive in practice. Importantly, SLICE retains a critical advantage of DICE in that its sample complexity only depends on quantities present in the information theoretic lower bound. We anticipate that this result will stimulate future search of computationally efficient sample-optimal algorithms.
Tasks
Published	2017-03-15
URL	http://arxiv.org/abs/1703.04886v3
PDF	http://arxiv.org/pdf/1703.04886v3.pdf
PWC	https://paperswithcode.com/paper/information-theoretic-optimal-learning-of
Repo
Framework

The UMCD Dataset


Title	The UMCD Dataset
Authors	Danilo Avola, Gian Luca Foresti, Niki Martinel, Daniele Pannone, Claudio Piciarelli
Abstract	In recent years, the technological improvements of low-cost small-scale Unmanned Aerial Vehicles (UAVs) are promoting an ever-increasing use of them in different tasks. In particular, the use of small-scale UAVs is useful in all these low-altitude tasks in which common UAVs cannot be adopted, such as recurrent comprehensive view of wide environments, frequent monitoring of military areas, real-time classification of static and moving entities (e.g., people, cars, etc.). These tasks can be supported by mosaicking and change detection algorithms achieved at low-altitude. Currently, public datasets for testing these algorithms are not available. This paper presents the UMCD dataset, the first collection of geo-referenced video sequences acquired at low-altitude for mosaicking and change detection purposes. Five reference scenarios are also reported.
Tasks
Published	2017-04-05
URL	http://arxiv.org/abs/1704.01426v1
PDF	http://arxiv.org/pdf/1704.01426v1.pdf
PWC	https://paperswithcode.com/paper/the-umcd-dataset
Repo
Framework

Feature Selection Parallel Technique for Remotely Sensed Imagery Classification


Title	Feature Selection Parallel Technique for Remotely Sensed Imagery Classification
Authors	Nhien-An Le-Khac, M-Tahar Kechadi, Bo Wu, C. Chen
Abstract	Remote sensing research focusing on feature selection has long attracted the attention of the remote sensing community because feature selection is a prerequisite for image processing and various applications. Different feature selection methods have been proposed to improve the classification accuracy. They vary from basic search techniques to clonal selections, and various optimal criteria have been investigated. Recently, methods using dependence-based measures have attracted much attention due to their ability to deal with very high dimensional datasets. However, these methods are based on Cramers V test, which has performance issues with large datasets. In this paper, we propose a parallel approach to improve their performance. We evaluate our approach on hyper-spectral and high spatial resolution images and compare it to the proposed methods with a centralized version as preliminary results. The results are very promising.
Tasks	Feature Selection
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03530v1
PDF	http://arxiv.org/pdf/1704.03530v1.pdf
PWC	https://paperswithcode.com/paper/feature-selection-parallel-technique-for
Repo
Framework

Detection Algorithms for Communication Systems Using Deep Learning


Title	Detection Algorithms for Communication Systems Using Deep Learning
Authors	Nariman Farsad, Andrea Goldsmith
Abstract	The design and analysis of communication systems typically rely on the development of mathematical models that describe the underlying communication channel, which dictates the relationship between the transmitted and the received signals. However, in some systems, such as molecular communication systems where chemical signals are used for transfer of information, it is not possible to accurately model this relationship. In these scenarios, because of the lack of mathematical channel models, a completely new approach to design and analysis is required. In this work, we focus on one important aspect of communication systems, the detection algorithms, and demonstrate that by borrowing tools from deep learning, it is possible to train detectors that perform well, without any knowledge of the underlying channel models. We evaluate these algorithms using experimental data that is collected by a chemical communication platform, where the channel model is unknown and difficult to model analytically. We show that deep learning algorithms perform significantly better than a simple detector that was used in previous works, which also did not assume any knowledge of the channel.
Tasks
Published	2017-05-22
URL	http://arxiv.org/abs/1705.08044v2
PDF	http://arxiv.org/pdf/1705.08044v2.pdf
PWC	https://paperswithcode.com/paper/detection-algorithms-for-communication
Repo
Framework